Merge tag 'bitmap-for-6.12' of https://github.com/norov/linux

Pull bitmap updates from Yury Norov:

 - switch all bitmamp APIs from inline to __always_inline (Brian Norris)

   The __always_inline series improves on code generation, and now with
   the latest compiler versions is required to avoid compilation
   warnings. It spent enough in my backlog, and I'm thankful to Brian
   Norris for taking over and moving it forward.

 - introduce GENMASK_U128() macro (Anshuman Khandual)

   GENMASK_U128() is a prerequisite needed for arm64 development

* tag 'bitmap-for-6.12' of https://github.com/norov/linux:
  lib/test_bits.c: Add tests for GENMASK_U128()
  uapi: Define GENMASK_U128
  nodemask: Switch from inline to __always_inline
  cpumask: Switch from inline to __always_inline
  bitmap: Switch from inline to __always_inline
  find: Switch from inline to __always_inline

include/linux/bits.h

@@ -36,4 +36,19 @@
 #define GENMASK_ULL(h, l) \
 	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
 
+#if !defined(__ASSEMBLY__)
+/*
+ * Missing asm support
+ *
+ * __GENMASK_U128() depends on _BIT128() which would not work
+ * in the asm code, as it shifts an 'unsigned __init128' data
+ * type instead of direct representation of 128 bit constants
+ * such as long and unsigned long. The fundamental problem is
+ * that a 128 bit constant will get silently truncated by the
+ * gcc compiler.
+ */
+#define GENMASK_U128(h, l) \
+	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l))
+#endif
+
 #endif	/* __LINUX_BITS_H */

include/linux/find.h

@@ -52,7 +52,7 @@ unsigned long _find_next_bit_le(const unsigned long *addr, unsigned
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
 			    unsigned long offset)
 {
@@ -81,7 +81,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_and_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
 		unsigned long offset)
@@ -112,7 +112,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1,
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_andnot_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
 		unsigned long offset)
@@ -142,7 +142,7 @@ unsigned long find_next_andnot_bit(const unsigned long *addr1,
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_or_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
 		unsigned long offset)
@@ -171,7 +171,7 @@ unsigned long find_next_or_bit(const unsigned long *addr1,
  * Returns the bit number of the next zero bit
  * If no bits are zero, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
 				 unsigned long offset)
 {
@@ -198,7 +198,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
  * Returns the bit number of the first set bit.
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
 {
 	if (small_const_nbits(size)) {
@@ -224,7 +224,7 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
  * Returns the bit number of the N'th set bit.
  * If no such, returns >= @size.
  */
-static inline
+static __always_inline
 unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n)
 {
 	if (n >= size)
@@ -249,7 +249,7 @@ unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsign
  * Returns the bit number of the N'th set bit.
  * If no such, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2,
 				unsigned long size, unsigned long n)
 {
@@ -276,7 +276,7 @@ unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *
  * Returns the bit number of the N'th set bit.
  * If no such, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
 				unsigned long size, unsigned long n)
 {
@@ -332,7 +332,7 @@ unsigned long find_nth_and_andnot_bit(const unsigned long *addr1,
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_first_and_bit(const unsigned long *addr1,
 				 const unsigned long *addr2,
 				 unsigned long size)
@@ -357,7 +357,7 @@ unsigned long find_first_and_bit(const unsigned long *addr1,
  * Returns the bit number for the first set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_first_and_and_bit(const unsigned long *addr1,
 				     const unsigned long *addr2,
 				     const unsigned long *addr3,
@@ -381,7 +381,7 @@ unsigned long find_first_and_and_bit(const unsigned long *addr1,
  * Returns the bit number of the first cleared bit.
  * If no bits are zero, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
 {
 	if (small_const_nbits(size)) {
@@ -402,7 +402,7 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
  *
  * Returns the bit number of the last set bit, or size.
  */
-static inline
+static __always_inline
 unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
 {
 	if (small_const_nbits(size)) {
@@ -425,7 +425,7 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
  * Returns the bit number for the next set bit, or first set bit up to @offset
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_and_bit_wrap(const unsigned long *addr1,
 					const unsigned long *addr2,
 					unsigned long size, unsigned long offset)
@@ -448,7 +448,7 @@ unsigned long find_next_and_bit_wrap(const unsigned long *addr1,
  * Returns the bit number for the next set bit, or first set bit up to @offset
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_bit_wrap(const unsigned long *addr,
 					unsigned long size, unsigned long offset)
 {
@@ -465,7 +465,7 @@ unsigned long find_next_bit_wrap(const unsigned long *addr,
  * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing
  * before using it alone.
  */
-static inline
+static __always_inline
 unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size,
 				 unsigned long start, unsigned long n)
 {
@@ -506,20 +506,20 @@ extern unsigned long find_next_clump8(unsigned long *clump,
 
 #if defined(__LITTLE_ENDIAN)
 
-static inline unsigned long find_next_zero_bit_le(const void *addr,
-		unsigned long size, unsigned long offset)
+static __always_inline
+unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset)
 {
 	return find_next_zero_bit(addr, size, offset);
 }
 
-static inline unsigned long find_next_bit_le(const void *addr,
-		unsigned long size, unsigned long offset)
+static __always_inline
+unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset)
 {
 	return find_next_bit(addr, size, offset);
 }
 
-static inline unsigned long find_first_zero_bit_le(const void *addr,
-		unsigned long size)
+static __always_inline
+unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
 {
 	return find_first_zero_bit(addr, size);
 }
@@ -527,7 +527,7 @@ static inline unsigned long find_first_zero_bit_le(const void *addr,
 #elif defined(__BIG_ENDIAN)
 
 #ifndef find_next_zero_bit_le
-static inline
+static __always_inline
 unsigned long find_next_zero_bit_le(const void *addr, unsigned
 		long size, unsigned long offset)
 {
@@ -546,7 +546,7 @@ unsigned long find_next_zero_bit_le(const void *addr, unsigned
 #endif
 
 #ifndef find_first_zero_bit_le
-static inline
+static __always_inline
 unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
 {
 	if (small_const_nbits(size)) {
@@ -560,7 +560,7 @@ unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
 #endif
 
 #ifndef find_next_bit_le
-static inline
+static __always_inline
 unsigned long find_next_bit_le(const void *addr, unsigned
 		long size, unsigned long offset)
 {

include/uapi/linux/bits.h

@@ -12,4 +12,7 @@
         (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \
          (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
 
+#define __GENMASK_U128(h, l) \
+	((_BIT128((h)) << 1) - (_BIT128(l)))
+
 #endif /* _UAPI_LINUX_BITS_H */

include/uapi/linux/const.h

@@ -28,6 +28,23 @@
 #define _BITUL(x)	(_UL(1) << (x))
 #define _BITULL(x)	(_ULL(1) << (x))
 
+#if !defined(__ASSEMBLY__)
+/*
+ * Missing asm support
+ *
+ * __BIT128() would not work in the asm code, as it shifts an
+ * 'unsigned __init128' data type as direct representation of
+ * 128 bit constants is not supported in the gcc compiler, as
+ * they get silently truncated.
+ *
+ * TODO: Please revisit this implementation when gcc compiler
+ * starts representing 128 bit constants directly like long
+ * and unsigned long etc. Subsequently drop the comment for
+ * GENMASK_U128() which would then start supporting asm code.
+ */
+#define _BIT128(x)	((unsigned __int128)(1) << (x))
+#endif
+
 #define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1)
 #define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))
 

lib/test_bits.c

@@ -39,6 +39,36 @@ static void genmask_ull_test(struct kunit *test)
 #endif
 }
 
+static void genmask_u128_test(struct kunit *test)
+{
+#ifdef CONFIG_ARCH_SUPPORTS_INT128
+	/* Below 64 bit masks */
+	KUNIT_EXPECT_EQ(test, 0x0000000000000001ull, GENMASK_U128(0, 0));
+	KUNIT_EXPECT_EQ(test, 0x0000000000000003ull, GENMASK_U128(1, 0));
+	KUNIT_EXPECT_EQ(test, 0x0000000000000006ull, GENMASK_U128(2, 1));
+	KUNIT_EXPECT_EQ(test, 0x00000000ffffffffull, GENMASK_U128(31, 0));
+	KUNIT_EXPECT_EQ(test, 0x000000ffffe00000ull, GENMASK_U128(39, 21));
+	KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, GENMASK_U128(63, 0));
+
+	/* Above 64 bit masks - only 64 bit portion can be validated once */
+	KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, GENMASK_U128(64, 0) >> 1);
+	KUNIT_EXPECT_EQ(test, 0x00000000ffffffffull, GENMASK_U128(81, 50) >> 50);
+	KUNIT_EXPECT_EQ(test, 0x0000000000ffffffull, GENMASK_U128(87, 64) >> 64);
+	KUNIT_EXPECT_EQ(test, 0x0000000000ff0000ull, GENMASK_U128(87, 80) >> 64);
+
+	KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, GENMASK_U128(127, 0) >> 64);
+	KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, (u64)GENMASK_U128(127, 0));
+	KUNIT_EXPECT_EQ(test, 0x0000000000000003ull, GENMASK_U128(127, 126) >> 126);
+	KUNIT_EXPECT_EQ(test, 0x0000000000000001ull, GENMASK_U128(127, 127) >> 127);
+#ifdef TEST_GENMASK_FAILURES
+	/* these should fail compilation */
+	GENMASK_U128(0, 1);
+	GENMASK_U128(0, 10);
+	GENMASK_U128(9, 10);
+#endif /* TEST_GENMASK_FAILURES */
+#endif /* CONFIG_ARCH_SUPPORTS_INT128 */
+}
+
 static void genmask_input_check_test(struct kunit *test)
 {
 	unsigned int x, y;
@@ -56,12 +86,16 @@ static void genmask_input_check_test(struct kunit *test)
 	/* Valid input */
 	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(1, 1));
 	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(39, 21));
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(100, 80));
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(110, 65));
+	KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(127, 0));
 }
 
 
 static struct kunit_case bits_test_cases[] = {
 	KUNIT_CASE(genmask_test),
 	KUNIT_CASE(genmask_ull_test),
+	KUNIT_CASE(genmask_u128_test),
 	KUNIT_CASE(genmask_input_check_test),
 	{}
 };